INDEX

Explanations

proper nouns or specialized terms, particularly related to locations or titles

oai_token-act-pair · gpt-3.5-turbo

empty strings or gaps in the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 caut

-0.62

untled

-0.58

 helicop

-0.57

 Beir

-0.57

 tremend

-0.54

 scrut

-0.53

 incorpor

-0.53

staking

-0.53

 seiz

-0.53

 undermin

-0.53

POSITIVE LOGITS

 âĵĺ

0.52

tones

0.49

IVERS

0.45

uties

0.44

 guiActiveUnfocused

0.43

malink

0.43

trip

0.43

TR

0.42

 Transgender

0.42

 âĢº

0.41

Activations Density 1.179%

proper nouns or specialized terms, particularly related to locations or titles

empty strings or gaps in the text

No Comments

No Known Activations